Wind energy is a vital pillar of modern sustainable power generation, yet wind turbine generators remain vulnerable to incipient inter-turn short-circuit (ITSC) faults in their stator windings. These faults can cause fluctuations in the output voltage, frequency, and power of wind turbines, eventually leading to overheating, equipment damage, and rising maintenance costs if not detected early. Although significant progress has been made in condition monitoring, the current methods still fall short of the robustness required for early fault diagnosis in complex operational settings. To address this gap, this study presents a novel deep learning framework that involves traditional baseline machine-learning algorithms and advanced deep network architectures to diagnose seven distinct ITSC fault types using signals from current, vibration, and axial magnetic flux sensors. Our approach is rigorously evaluated using metrics such as confusion matrices, accuracy, recall, average precision (AP), mean average precision (mAP), hypothesis testing, and feature visualization. The experimental results demonstrate that deep learning models outperform machine learning algorithms in terms of precision and stability, achieving an mAP of 99.25% in fault identification, with three-phase current signals emerging as the most reliable indicator of generator faults compared to vibration and electromagnetic data. It is recommended to combine three-phase current sensors with deep learning frameworks for the precise identification of various types of incipient ITSC faults. This study offers a robust and efficient pipeline for condition monitoring and ITSC fault diagnosis, enabling the intelligent operation of wind turbines and maintenance of their operating states. Ultimately, it contributes to providing a practical way forward in enhancing turbine reliability and lifespan.

Real-time insulator defect detection is critical for ensuring the reliability and safety of power transmission systems. However, deploying deep learning models on edge devices presents significant challenges due to limited computational resources and strict latency constraints. To address these issues, we propose YOLOLS, a lightweight and efficient detection model derived from YOLOv8n and optimized for real-time edge deployment. Specifically, YOLOLS integrates GhostConv to generate feature maps through stepwise convolution, reducing computational redundancy while preserving representational capacity. Moreover, the C2f module is restructured into a ResNet–RepConv architecture, in which convolution and Batch Normalization layers are fused during inference to reduce model complexity and enhance inference speed. To further optimize performance, a lightweight shared-convolution detection head significantly reduces parameter count and computational cost without compromising detection accuracy. Additionally, an auxiliary bounding box mechanism is incorporated into the CIoU loss function, improving both convergence speed and localization precision. Experimental validation on the CPLID dataset demonstrates that YOLOLS achieves a 42.4% reduction in parameters and a 48.1% decrease in FLOPs compared to YOLOv8n while maintaining a high mAP of 91%. Furthermore, when deployed on Jetson Orin NX, YOLOLS achieves 44.6 FPS, ensuring real-time processing capability. Compared to other lightweight YOLO variants, YOLOLS achieves a better balance between accuracy, computational efficiency, and inference speed, making it an optimal solution for real-time insulator defect detection in resource-constrained edge computing environments.

Mechanical failure prediction of lithium-ion batteries (LIBs) can provide important maintenance information and decision-making reference in battery safety management. However, the complexity of the internal structure of batteries poses challenges to the generalizability and prediction accuracy of traditional mechanical models. In view of these challenges, emerging data-driven methods provide new ideas for the failure prediction of LIBs. This study is based on an experimental data-driven application of machine learning (ML) models to rapidly predict the mechanical behavior and failure of cylindrical cells under different loading conditions. Mechanical abuse experiments including local indentation, flat compression, and three-point bending experiments were conducted on cylindrical LIB samples, and mechanical failure datasets for cylindrical cells were generated, including displacements, voltages, temperatures, and mechanical forces. Six ML models were used to predict the mechanical behavior of cylindrical batteries, four metrics were used to evaluate the prediction performance, the coefficients of determination of eXtreme Gradient Boosting (XGBoost) regression and random forest were 0.999, and the root-mean-square errors (RMSE) were lower than 0.015. It is shown that the integrated tree models tested in this study are suitable for the failure prediction of LIBs under the conditions of mechanical abuse. Also, the random forest prediction model outperforms other ML prediction models with the smallest RMSE values of 0.005, 0.0149, and 0.007 for local indentation, flat compression, and three-point bending, respectively. This work highlights the capability of ML algorithms for LIB safety prediction.

Rotary-clamp spacers used in bundled conductors of large-span ultra-high-voltage transmission lines are exposed to long-term wind-induced low-frequency cyclic vibration, under which progressive wear at connection interfaces may threaten structural reliability. This study examines the wear evolution behavior of a rotary-clamp spacer applied in 1000 kV six-bundled conductors by integrating field failure evidence with controlled fatigue vibration experiments. Field inspections reveal that damage is consistently localized at pin–hole interfaces of rotary clamps and exhibits pronounced directional characteristics. To reproduce these features under laboratory conditions, long-duration cyclic vibration tests were conducted using representative loading configurations, allowing quantitative characterization of hole enlargement and wear morphology evolution. The experimental results show a clear transition in wear behavior with increasing cycle number, accompanied by distinct responses between central and side pin holes associated with different contact conditions. Through combined experimental observation and mechanical interpretation, this work provides a coherent description of wear-dominated degradation processes in rotary-clamp spacers and offers insight into the origins of directionally concentrated in-service damage under wind-induced vibration.

Deformation monitoring of Gas-Insulated Transmission Lines (GILs) is critical for the early detection of structural issues and for ensuring safe power transmission. In this study, we introduce a rapid monocular measurement method that leverages deep learning for real-time monitoring. A YOLOv10 model is developed for automatically identifying regions of interest (ROIs) that may exhibit deformations. Within these ROIs, grayscale data is used to dynamically set thresholds for FAST corner detection, while the Shi–Tomasi algorithm filters redundant corners to extract unique feature points for precise tracking. Subsequent subpixel refinement further enhances measurement accuracy. To correct image tilt, ArUco markers are employed for geometric correction and to compute a scaling factor based on their known edge lengths, thereby reducing errors caused by non-perpendicular camera angles. Simulated experiments validate our approach, demonstrating that combining refined ArUco marker coordinates with manually annotated features significantly improves detection accuracy. Our method achieves a mean absolute error of no more than 1.337 mm and a processing speed of approximately 0.024 s per frame, meeting the precision and efficiency requirements for GIL deformation monitoring. This integrated approach offers a robust solution for long-term, real-time monitoring of GIL deformations, with promising potential for practical applications in power transmission systems.

Transmission-line inspection requires a single detector to localize complete insulator strings together with much smaller broken-shell and flashover-damaged regions. These targets differ in spatial extent and in their dependence on local detail and surrounding context, which complicates cross-scale feature fusion when accurate bounding boxes are required. This study develops receptive-field-aware path aggregation (PRA) and bidirectional receptive-field-aware aggregation (BRA), combining path aggregation with receptive-field expansion and adaptive scale weighting. Compared with the path aggregation network (PANet), PRA increases mean average precision (mAP) at an intersection-over-union (IoU) threshold of 0.5 (mAP@0.5) by 2.2 percentage points and mAP averaged over IoU thresholds from 0.5 to 0.95 (mAP@0.5: 0.95) by 4.6 points; BRA produces gains of 1.5 and 4.0 points, respectively. The highest mAP@0.5:0.95 of 91.3% is jointly achieved by Swin-T-PRA + Alpha-CIoU and Swin-T-BRA + Alpha-CIoU, with corresponding mAP@0.5 values of 98.6% and 98.5% and model-only inference speeds of 48.5 and 48.3 FPS on an RTX 3080 Ti, respectively. The larger gains across stricter IoU thresholds indicate that PRA/BRA provide greater benefits when more stringent box-overlap criteria are imposed, although the present evaluation does not independently isolate the bounding-box regression mechanism.